monuszero

I sloppily glommed a lot together there.

The pdf parsing was certainly the least mature capability of those that I mentioned. Got decent results with the pdf parsing tool that ships with Claude (desktop) but ultimately wrote a subagent definition to help with pdf parsing. I found myself sticking to vendors with the most parseable (or ideally html) datasheets formats TI, AD, Microchip all fine - but I did learn to love Wurth Elektronik. I looked into doing a custom RAG solution for this.. docling etc. to smooth over things like tables split between pages, Figure reading. Ultimately found their team to be responsive on discord and figured they have every incentive to solve this for me by the next time I find time for a hobby electronics project.

Generally the llms were awesome at discovering the chips I needed (with a few hallucinations promptly uncovered - like a TI mux chip which didn’t exist in the automotive grade designation for that package) without a doubt shortened my search and design development time by some large factor. I remember some AWESOME solo distance driving where i voice chatted with GPT 5x doing thinks like picking the right RS485 driver ic and microcontroller pairing without needed to wade through datasheets

The python is less in need of explanation I’m sure

We had a monthlong sprint adding robot motion planning features to our codebase years ago, and I was never satisfied with the result. As a small team wanting to leverage oss we vendored in OMPL, did the usual thing around caching and roadmap management. I knew there was a way to parallelize some of the algorithm we were using with simd or a gpu kernel, plenty of that in the literature, but it was never worth fighting CUDA or metal/accelerate or whatever for uncertain gains.

So when cooking dinner one night, I set opus 4.6 on a from-scratch native and accelerated roadmap planner implementation (after previously porting IK, FK, collision checking with some success) I had primed it by having a research agent drop a literature review in its docs folder covering the type of planner we needed. By the time the pasta water was boiling it was done- getting plans in a few hundred ms compared to several of seconds on our good old fashioned OMPL code.

For me it was the revelation that the economic value of cooking dinner could be compared to tackling an honest two weeks of coding work. The calculus has shifted - work that was once a risky or extravagant use of time is now worth considering.

For a small team who wants to focus on substance rather than implementation, knows what they want, and how to set up the agent for success, it’s a complete game changer in terms of what we can take on. Incumbents beware

That precise mixed technique approach has worked well for me. I’ve been using JITX (python based circuit design with a powerful auto router). Free for personal use, and has been discussed a few times here in HN.

Edit: it’s almost assumed at this point but for completeness Claude / Codex were the ones driving the OO python code and datasheet research and parsing.

https://www.jitx.com/

Not sure if an oblaque tomb raider reference or math metaphor.

So, Aaed was our intern last summer - and he’s the real deal. I got to work with him on some really cool bespoke robotic end-effectors and the guy has great design instincts. Picked up mechatronics skills like a sponge, grokked hamming codes in like 30sec from a whiteboard doodle. Super hard worker too, he would stay late in the electronics lab to work on the motor design for what turned out to be CARA - we had fun testing the backlash one evening and ever since I’ve been trying to shoehorn one of those actuators into a project.

Potential and active founders here should consider reaching out (i think a startup setting would suit him better than corporate research), though he’s obviously got his own stuff going on and a degree to finish!

[current employee of Autodesk] Minor contributions to existing OSS are generally encouraged day-to-day by employees.

There are also more strategic open source initiatives such as the USD stuff covered here.

Many of us, especially in the research division, would love to put more code out there. (For example some tools that we use internally) The good news on this front is that there is now a sanctioned process for this to happen, and the attitude seems much warmer than when I joined a decade ago.

I’m personally involved in trying to open source some of my own work in the robotics domain, and have been pleasantly surprised with the response.